xianyu_publish

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the bash tool to run a local Python module (src.cli) located in the /home/node/.openclaw/workspace directory.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to an unvalidated command-line interface surface (Category 8).
  • Ingestion points: Product metadata provided by the user, such as the title, price, description, and tags, is directly interpolated into a bash command string.
  • Boundary markers: While double quotes are used in the command template, the skill lacks instructions for the agent to sanitize or escape shell-sensitive characters like backticks or dollar signs.
  • Capability inventory: The agent possesses the capability to execute shell commands via the bash tool.
  • Sanitization: No input validation or sanitization requirements are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 03:31 AM